© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29409
    Prev
    Next
    INDEX
    Explanations

    falling in love with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    CHED
    -0.10
    iffe
    -0.09
     noon
    -0.08
    볨
    -0.08
    cef
    -0.08
    äºĨ解ä¸Ģä¸ĭ
    -0.08
    åģ»
    -0.08
    amat
    -0.08
     Creed
    -0.08
    arning
    -0.08
    POSITIVE LOGITS
    IMA
    0.10
    anson
    0.09
    ernet
    0.09
    çļ®èĤ¤çĹħ
    0.09
    åŨ
    0.09
    swith
    0.09
    iped
    0.08
    æĿ¥ä¸įåıĬ
    0.08
    ä¸Ģ对ä¸Ģ
    0.08
    æĭ¨
    0.08
    Activations Density 0.048%

    No Known Activations